Cover Image

RL Fine-Tuning Heals OOD Forgetting in SFT

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Jin, Hangzhan, Luan, Sitao, Ni, Tianwei, Lyu, Sicheng, Rabusseau, Guillaume, Rabbany, Reihaneh, Precup, Doina, Hamdaqa, Mohammad
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Rotation-Preserving Supervised Fine-Tuning
by: Jin, Hangzhan, et al.
Published: (2026)

RL Is Neither a Panacea Nor a Mirage: Understanding Supervised vs. Reinforcement Learning Fine-Tuning for LLMs
by: Jin, Hangzhan, et al.
Published: (2025)

CCCI: Code Completion with Contextual Information for Complex Data Transfer Tasks Using Large Language Models
by: Jin, Hangzhan, et al.
Published: (2025)

Higher-Order Transformers With Kronecker-Structured Attention
by: Omranpour, Soroush, et al.
Published: (2024)

Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
by: Luo, Ziyan, et al.
Published: (2025)

Higher Order Transformers: Enhancing Stock Movement Prediction On Multimodal Time-Series Data
by: Omranpour, Soroush, et al.
Published: (2024)

Diversity-Enriched Option-Critic
by: Kamat, Anand, et al.
Published: (2020)

Functional Acceleration for Policy Mirror Descent
by: Chelu, Veronica, et al.
Published: (2024)

A Look at Value-Based Decision-Time vs. Background Planning Methods Across Different Settings
by: Alver, Safa, et al.
Published: (2022)

ReactZyme: A Benchmark for Enzyme-Reaction Prediction
by: Hua, Chenqing, et al.
Published: (2024)

Kurtosis-Guided Denoising Score Matching for Tabular Anomaly Detection
by: Livernoche, Victor, et al.
Published: (2026)

ROSA: Random Subspace Adaptation for Efficient Fine-Tuning
by: Hameed, Marawan Gamal Abdel, et al.
Published: (2024)

TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
by: Chmura, Jacob, et al.
Published: (2025)

Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection
by: Yang, Zachary, et al.
Published: (2025)

Towards Detecting Contextual Real-Time Toxicity for In-Game Chat
by: Yang, Zachary, et al.
Published: (2023)

Sparse-Reg: Improving Sample Complexity in Offline Reinforcement Learning using Sparsity
by: Arnob, Samin Yeasar, et al.
Published: (2025)

Adaptive Exploration for Data-Efficient General Value Function Evaluations
by: Jain, Arushi, et al.
Published: (2024)

Partial Models for Building Adaptive Model-Based Reinforcement Learning Agents
by: Alver, Safa, et al.
Published: (2024)

TN-SHAP-G: Graph-Structured Tensor Network Surrogates for Shapley Values and Interactions
by: Heidari, Farzaneh, et al.
Published: (2026)

SCAR: Shapley Credit Assignment for More Efficient RLHF
by: Cao, Meng, et al.
Published: (2025)

Combining Confidence Elicitation and Sample-based Methods for Uncertainty Quantification in Misinformation Mitigation
by: Rivera, Mauricio, et al.
Published: (2024)

Fluid-Agent Reinforcement Learning
by: Sharma, Shishir, et al.
Published: (2026)

Parseval Regularization for Continual Reinforcement Learning
by: Chung, Wesley, et al.
Published: (2024)

EnzymeFlow: Generating Reaction-specific Enzyme Catalytic Pockets through Flow Matching and Co-Evolutionary Dynamics
by: Hua, Chenqing, et al.
Published: (2024)

SFT-GO: Supervised Fine-Tuning with Group Optimization for Large Language Models
by: Kim, Gyuhak, et al.
Published: (2025)

Rejecting Hallucinated State Targets during Planning
by: Zhao, Mingde, et al.
Published: (2024)

Ask before you Build: Rethinking AI-for-Good in Human Trafficking Interventions
by: Nair, Pratheeksha, et al.
Published: (2025)

Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
by: Zhang, Shuyuan, et al.
Published: (2025)

UTG: Towards a Unified View of Snapshot and Event Based Models for Temporal Graphs
by: Huang, Shenyang, et al.
Published: (2024)

GeoLocSFT: Efficient Visual Geolocation via Supervised Fine-Tuning of Multimodal Foundation Models
by: Yi, Qiang, et al.
Published: (2025)

Mixtures of Experts Unlock Parameter Scaling for Deep RL
by: Obando-Ceron, Johan, et al.
Published: (2024)

RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
by: Matsutani, Kohsei, et al.
Published: (2025)

ControBench: An Interaction-Aware Benchmark for Controversial Discourse Analysis on Social Networks
by: Thuy, Ta Thanh, et al.
Published: (2026)

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning
by: Hong, Joey, et al.
Published: (2024)

Upweighting Easy Samples in Fine-Tuning Mitigates Forgetting
by: Sanyal, Sunny, et al.
Published: (2025)

Overcoming Forgetting in LLM Fine-Tuning with Evolution Strategies
by: Schweighofer, Kajetan, et al.
Published: (2026)

GPS-SSL: Guided Positive Sampling to Inject Prior Into Self-Supervised Learning
by: Feizi, Aarash, et al.
Published: (2024)

Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
by: Carr, Jonathan Colaço, et al.
Published: (2026)

PathOCL: Path-Based Prompt Augmentation for OCL Generation with GPT-4
by: Abukhalaf, Seif, et al.
Published: (2024)

Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation
by: Patil, Gandharv, et al.
Published: (2022)